Abstract
Dialog Manager has played a great role in conversational AI so much, so that it is also called the heart of a dialog system. It has been employed in task-oriented Chatbot to learn the context of a conversation and come up with some representation which helps in executing the task. For example, booking a restaurant table, flight booking, movie tickets, etc. In this paper, a dialog manager is trained in a supervised manner in order to predict the best response given the latent state representation of the user message. The latent representation is formed by the Convolution Neural Network (CNN) and Bidirectional Long Short Term Memory network (BiLSTM) with attention. An ablation study is conducted with three different architectures. One of them achieved a state-of-the-art result in turn accuracy on babI6 dataset and dialog accuracy equivalent to the baseline model.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
